© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94441
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to relationships and interactions between individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymes
    -0.07
    oj
    -0.07
    ogram
    -0.06
    utron
    -0.06
    ürn
    -0.06
    oon
    -0.06
    ulo
    -0.06
    occ
    -0.05
     LH
    -0.05
    és
    -0.05
    POSITIVE LOGITS
    fillType
    0.08
    ../../../
    0.07
    latlong
    0.07
    -lite
    0.07
    967
    0.07
    thalm
    0.07
    /UIKit
    0.07
    atos
    0.06
     similarly
    0.06
    $_['
    0.06
    Activations Density 0.029%

    No Known Activations